An Exploratory Application of Constraint Optimization in Mozart to Probabilistic Natural Language Processing

Langkilde-Geary, Irene

doi:10.1007/11424574_11

Cited by 5 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(We will return to this point at various places in this paper.) Constraints are particularly well-suited for addressing problems that involve interactions between information of different types, granularity and levels of specification (see Langkilde-Geary, 2004). …”

Section: Constraints In Generation: Motivation Limitations and Complmentioning

confidence: 99%

Generating under Global Constraints: the Case of Scripted Dialogue

Piwek

Deemter

2007

Res on Lang and Comput

View full text Add to dashboard Cite

Recently, the view of Natural Language Generation (nlg) as a Constraint Satisfaction Problem (csp) has seen something of a revival. The aim of this paper is to examine the issues that arise when nlg is viewed as a csp, and to introduce a novel application of constraint-based nlg, namely the Scripted Dialogue. Scripted Dialogue shares a number of crucial features with discourse, which make it possible to control the global properties of a computer-generated dialogue in the same way as those of a generated discourse. We pay particular attention to the use of soft constraints for enforcing global properties of text and dialogue. Because there has been little research into the formal properties of soft constraints in relation to generation, we start out with a theoretical exploration. We argue that, when multiple constraints are involved, it is important to define properly what is being optimised before proposing specific algorithms, and we argue that such definitions are often lacking in csp-based nlg. We show that it can be difficult (and sometimes even impossible) to guarantee satisfaction of global constraints by following local strategies. Based on these difficulties, we propose a novel approach to the generation of discourse and dialogue which combines csp solving with revision. Scripted Dialogue is used to illustrate this approach, which is compared with alternatives such as monitoring and estimation.

show abstract

Section: Constraints In Generation: Motivation Limitations and Complmentioning

confidence: 99%

Generating under Global Constraints: the Case of Scripted Dialogue

Piwek

Deemter

2007

Res on Lang and Comput

View full text Add to dashboard Cite

show abstract

“…We previously implemented an exploratory prototype that used raw frequencies instead of smoothed probabilities for the feature costs and search heuristic confidences. (Langkilde-Geary, 2005;Langkilde-Geary, 2007). The lack of smoothing severely limited the applicability of the prototype.…”

Section: Methodsmentioning

confidence: 99%

A constraint programming approach to probabilistic syntactic processing

Langkilde-Geary¹

2009

Proceedings of the Workshop on Integer Linear Programming for Natural Langauge Processing - ILP '09

Self Cite

View full text Add to dashboard Cite

“…There are essentially three approaches to trainable surface realization: two-stage surface realizers [8,9,10], classification-based surface realizers [11,12], and surface realizers that use probabilistic grammars [13,14,15,16]. Each type of surface realizer uses a statistical model or set of models that capture word order and syntactic constraints (e.g.…”

Section: Related Workmentioning

confidence: 99%

Where do thewords come from? Learning models for word choice and ordering from spoken dialog corpora

Stent

Bangalore

Fabbrizio

2008

2008 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

Most existing generation systems for spoken dialog require the system engineer to specify by hand the words to be used in system prompts. However, the existence of corpora of spoken dialog makes it possible to acquire the words and structure of system prompts automatically. In this paper, we construct statistical models for generating system prompts, both for word choice and for word ordering. We evaluate these models using a human-computer dialog multicorpus and a human-human dialog corpus. Our results show that statistical models for word choice can work well, while more work is needed on statistical models for word ordering.

show abstract

An Exploratory Application of Constraint Optimization in Mozart to Probabilistic Natural Language Processing

Cited by 5 publications

References 2 publications

Generating under Global Constraints: the Case of Scripted Dialogue

Generating under Global Constraints: the Case of Scripted Dialogue

A constraint programming approach to probabilistic syntactic processing

Where do thewords come from? Learning models for word choice and ordering from spoken dialog corpora

Contact Info

Product

Resources

About